# When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning

arXiv: https://arxiv.org/abs/2609.15305 · HTML: https://mlsanity.com/paper/2609.15305/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2005.03545/) (2020)
- [Interventional Causal Representation Learning](https://mlsanity.com/paper/2209.11924/) (2022)
- [Causality Inspired Representation Learning for Domain Generalization](https://mlsanity.com/paper/2203.14237/) (2022)
- [Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment](https://mlsanity.com/paper/2309.13378/) (2023)
- [Causal Discovery from Temporal Data: An Overview and New Perspectives](https://mlsanity.com/paper/2303.10112/) (2023)
- [Unsupervised Path Representation Learning with Curriculum Negative Sampling](https://mlsanity.com/paper/2106.09373/) (2021)
- [Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction](https://mlsanity.com/paper/2204.08587/) (2022)
- [Multi-Graph Fusion Networks for Urban Region Embedding](https://mlsanity.com/paper/2201.09760/) (2022)
- [LightPath: Lightweight and Scalable Path Representation Learning](https://mlsanity.com/paper/2307.10171/) (2023)
- [HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecasting](https://mlsanity.com/paper/2109.12846/) (2021)
- [Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version](https://mlsanity.com/paper/2203.16110/) (2022)
- [Causal conditional hidden Markov model for multimodal traffic prediction](https://mlsanity.com/paper/2301.08249/) (2023)
- [MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version](https://mlsanity.com/paper/2411.18428/) (2024)
- [Continual Causal Inference with Incremental Observational Data](https://mlsanity.com/paper/2303.01775/) (2023)
- [FlexiReg: Flexible Urban Region Representation Learning](https://mlsanity.com/paper/2503.09128/) (2025)
- [Urban Region Representation Learning with Attentive Fusion](https://mlsanity.com/paper/2312.04606/) (2023)
- [CGAP: Urban Region Representation Learning with Coarsened Graph Attention Pooling](https://mlsanity.com/paper/2407.02074/) (2024)
- [MEGAN: A Generative Adversarial Network for Multi-View Network Embedding](https://mlsanity.com/paper/1909.01084/) (2019)
- [CausalTAD: Causal Implicit Generative Model for Debiased Online Trajectory Anomaly Detection](https://mlsanity.com/paper/2412.18820/) (2024)
- [PathRank: A Multi-Task Learning Framework to Rank Paths in Spatial Networks](https://mlsanity.com/paper/1907.04028/) (2019)
- [Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach](https://mlsanity.com/paper/2505.17637/) (2025)
- [Spatio-Temporal Trajectory Foundation Model - Recent Advances and Future Directions](https://mlsanity.com/paper/2511.20729/) (2025)
- [DiffMM: Efficient Method for Accurate Noisy and Sparse Trajectory Map Matching via One Step Diffusion](https://mlsanity.com/paper/2601.08482/) (2026)
- [Spatial-Temporal Cross-View Contrastive Pre-training for Check-in Sequence Representation Learning](https://mlsanity.com/paper/2407.15899/) (2024)
- [ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2602.06240/) (2026)
- [REFINE: Trajectory Representation Learning via Closed-Loop Transcription -- Extended Version](https://mlsanity.com/paper/2609.07206/) (2026)
- [DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version](https://mlsanity.com/paper/2609.07316/) (2026)

## Abstract (arXiv)

Urban region representation learning commonly combines heterogeneous data sources, such as mobility flows, points of interest, and land-use information, to support tasks including mobility analysis, public safety forecasting, and service demand estimation. Existing multi-view methods typically improve region embeddings by strengthening interactions across views. However, such methods often overlook view-specific regional structures and may propagate correlations induced by shared latent factors, which can reduce the stability of downstream predictions. To overcome this major limitation, we propose CURE, a confounder-aware framework for multi-view urban region representation learning. CURE first encodes each view with its regional graph structure, estimates a shared latent component, and then reduces its projected influence before cross-view interaction. A hierarchical graph-aware fusion module subsequently aggregates the residual view representations using local and global regional contexts Experiments on three real-world cities show that CURE improves predictive performance, remains robust under missing and noisy input views, and provides reliable cross-view integration through shared component separation and context-dependent view weighting.